Skip to content
Cortex SEMACortex SEMA

§1. Design principles

MarkdownOpen in ChatGPTOpen in Claude

Generated from docs/LANGUAGE.md §1. This is the normative specification; for a guided tour see the Language and Neurosymbolic sections.

Eight principles, each grounded in the corpus. Every construct in §5 must satisfy all of them.

  1. Probabilistic under the hood, deterministic at the boundary. Every construct has a nonempty deterministic guarantee column — no Sema construct is purely statistical. The guarantee map (05 §5) is generated by one rule: a generative result’s guarantee level equals the strongest sound check applied to it (verifier-inheritance, 05 §4.4).
  2. Enforced, never advisory. SymbolicAI’s @contract records failure but never blocks execution — DbC as advice (01 §6); Claude Code documents that natural-language rules are “context, not enforced configuration” (03). In Sema, a value that fails its contract is typed as failed and cannot flow into non-handling code. A library cannot make validation non-bypassable; a compiler can. That is the reason Sema is a language.
  3. Honest grading. Statistical verdicts are typed as statistical and carry their evidence (score, judge identity, threshold, calibration set, α). A fuzzy bool silently cast to bool — SymbolicAI’s ProbabilisticBooleanMode word-matching (01 §3) — is a language-level defect class Sema eliminates by construction.
  4. Pinned judges. semantics(), ~=, and every model-evaluated predicate denote a pinned judge (model hash + prompt + threshold + calibration set), making evaluation total and reproducible; judge-vs-intent agreement is a separate, quantified statistical question (05 §1.4). Changing a judge is a semver-major change to program semantics.
  5. The model proposes, the toolchain disposes. Every LLM-produced artifact (test, patch, translation, output) passes deterministic execution filters before it enters the build or the dataflow — Meta’s Assured-LLMSE discipline, which is what made 73% human acceptance possible (09 §2.5). LLM self-assessment is banned from any acceptance path (10).
  6. Accrete determinism. Statistical and adversarial findings are distilled into permanent deterministic artifacts (counterexamples, killed mutants, regression properties); a Sema codebase’s verification substrate hardens monotonically (09 §7.2).
  7. Familiar surface, honest divergence. Pythonic syntax, explicitly not a Python superset — Mojo’s landing position, never its launch position (12 §1). LLM authors are first-class: the grammar ships as a constrained-decoding artifact and the spec as the generator corpus (12 §6).
  8. No super-Turing claims. Sema + computable model oracles is exactly Turing-equivalent; the oracle framing buys a query/trust/substitutability boundary, not power (05 §1.2, arXiv:2406.12213).